القائمة
Format, lint, and fix all warnings across the entire codebase — including test files and pre-existing issues.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Query an independent peer or a configurable local/OpenRouter review panel, with distinct quorum and evidence-backed consensus interpretation policies.
Safely coordinate bounded delegation while preserving observable outcome and acceptance-evidence pairs through one-writer execution, independent review, and parent validation. Explicit invocation only.
Detect whether a beads repository needs classic-to-Dolt migration or an in-place Dolt schema upgrade.
Migrate beads from classic SQLite/JSONL to Dolt, or safely upgrade an existing Dolt schema after a bd upgrade.
Read-only current-session and UTC-week token telemetry dashboard for Pi, Claude Code, Codex, and optional OpenRouter management analytics.
Read-only audit of Pi routing and configured second-opinion panel model IDs against the active Pi catalog and public live model metadata; reports when Pi or configured models merit review without editing config.
| name | clean-code |
| description | Format, lint, and fix all warnings across the entire codebase — including test files and pre-existing issues. |
| allowed-tools | Read,Edit,Grep,Glob,Bash(make:*),AskUserQuestion |
| model-tier | standard |
| model | sonnet |
| effort | high |
| version | 1.1.0 |
| author | flurdy |
Format, lint, and fix all warnings across the entire codebase — including test files and pre-existing issues.
/clean-code
Each project defines a make clean-code Makefile target with the appropriate tooling for its language/stack.
make clean-code
If make clean-code fails or reports warnings/errors that couldn't be auto-fixed, investigate and fix them manually. Do NOT leave any warnings unresolved.
Re-run the target to confirm it passes cleanly:
make clean-code
It must exit with zero warnings and zero errors.
eslint-disable, #[allow(...)], @SuppressWarnings) unless there is a genuine false positive with a clear justification